Responses API and Codex - NexusAPI 文档中心

/v1/responses is not a universal “newer chat API.” In NexusAPI, it is primarily for the custom Provider configured in the Codex CLI guide, or for a model, key group, and channel that are explicitly confirmed to support the Responses protocol.

Confirm the model and channel firstDo not use /v1/responses for current Anthropic-type Claude channels. If you receive status_code=500, not implemented, use Chat Completions, or let Claude Code use native Messages configuration instead.

Endpoint and scope

POST https://nexusapi.link/v1/responses

Scenario	Recommended approach
Codex CLI	Use the `wire_api = "responses"` Provider configuration in the Codex CLI guide
Another app with a model confirmed for Responses	Use that app’s Responses client or schema and verify a minimum request first
General OpenAI-compatible text app	Use Chat Completions; do not switch just because this API is newer
Anthropic-type Claude	Use Messages or Chat Completions, not this endpoint

Minimum verification request

Only after model and channel support have been confirmed, test connectivity with:

curl 'https://nexusapi.link/v1/responses' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{
    "model": "YOUR_RESPONSES_MODEL_ID",
    "input": "Reply only: connection succeeded"
  }'

input is not the same field as Chat Completions messages, and the response must not be parsed as choices[0].message. Use the Apifox API reference or your client’s official schema for complete fields, streaming events, and result handling.

Codex CLI configuration essentials

model_provider = "nexusapi"
model = "YOUR_MODEL_ID"

[model_providers.nexusapi]
base_url = "https://nexusapi.link/v1"
env_key = "NEXUSAPI_API_KEY"
wire_api = "responses"

Keep the key in the NEXUSAPI_API_KEY environment variable, never in config.toml or auth.json. See the Codex CLI guide for installation, OS-specific environment variables, and verification.

What to check first

The key group contains the model and the model ID exactly matches the Model Marketplace.
The client actually requests /v1/responses, not /v1/v1/....
The model is confirmed to support Responses; use a different protocol for Anthropic-type Claude.
Keep the Request ID, client version, and complete error text, then follow the self-check guide.